International Journal of Modern Education and Computer Science (IJMECS)
IJMECS Vol. 16, No. 4, 8 Aug. 2024
Cover page and Table of Contents: PDF (size: 753KB)
A Hybrid Method based on Rules and Deep Learning for Enhancing Single-Word and Multi-Word Aspects Extraction from French Reviews
PDF (753KB), PP.1-16
Views: 0 Downloads: 0
Author(s)
Index Terms
aspect extraction, single-word aspect, multi-word aspect, hybrid method, filtering algorithm
Abstract
In recent years, Aspect Based Sentiment Analysis (ABSA) has gained significant importance, particularly for enterprises operating in the commercial domain. These enterprises tend to analyze the customers’ opinions concerning the different aspects of their products. The primary objective of ABSA is to first identify the aspects (such as battery) associated with a given product (such as a smartphone) and then assign a sentiment polarity to each aspect. In this paper, we focus on the Aspects Extraction (AE) task, specifically for the French language. Previous research studies have mainly focused on the extraction of single-word aspects without giving significant attention to the multi-word aspects. To address this issue, we propose a hybrid method that combines linguistic knowledge-based methods with deep learning-based methods to identify both single-word aspects and multi-word aspects. Firstly, we combined a set of rules with a deep learning-based model to extract the candidate aspects. Subsequently, we introduced a new filtering algorithm to detect the single-word aspect terms. Finally, we created a set of 52 patterns to extract the multi-word aspect terms. To evaluate the performance of the proposed hybrid method, we collected a dataset of 2400 French mobile phone comments from the Amazon website. The final outcome proves the encouraging results of the proposed hybrid method for both mobile phones (F-measure value: 87.27% for single-word aspects and 82.38% for multi-word aspects) and restaurants (F-measure value: 78.79% for single-word aspects and 76.04% for multi-word aspects) domains. By highlighting the practical implications of these results, our hybrid method offers a promising outlook for Aspect Based Sentiment Analysis task, opening new avenues for businesses and future research.
Cite This Paper
Hammi Sarsabene, Hammami M. Souha, Belguith H. Lamia, "A Hybrid Method based on Rules and Deep Learning for Enhancing Single-Word and Multi-Word Aspects Extraction from French Reviews", International Journal of Modern Education and Computer Science(IJMECS), Vol.16, No.4, pp. 1-16, 2024. DOI:10.5815/ijmecs.2024.04.01
Reference
[1]M. Hu and B. Liu, “Mining and summarizing customer reviews”, Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, 2004, pp. 168-177, doi: 10.1145/1014052.1014073.
[2]G. Qiu, B. Liu, J. Bu, and C. Chen, “Opinion word expansion and target extraction through double propagation”, Computational linguistics, vol. 37(1), pp. 9-27, 2011, doi: 10.1162/cola00034.
[3]S. Shariaty, and S. Moghaddam, “Fine-grained opinion mining using conditional random fields”, IEEE 11th International Conference on Data Mining Workshops, 2011, pp. 270-277, doi: 10.1109/ICDMW.2011.85.
[4]A. Banjar, Z. Ahmed, A. Daud, R. Abbasi, and H. Dawood, “Aspect-based sentiment analysis for polarity estimation of customer reviews on Twitter”, Computers, Materials and Continua, vol. 67, pp. 2023-2225, 2021, doi: 10.32604/cmc.2021.014226.
[5]M. Tubishat, N. Idris, and M.A. Abushariah, “Implicit aspect extraction in sentiment analysis: Review, taxonomy, opportunities, and open challenges”, Information Processing and Management, vol. 54, pp. 545-563, 2018, doi: 10.1016/j.ipm.2018.03.008.
[6]A. Banjar, Z. Ahmed, A. Daud, R. Abbasi, and H. Dawood, “Aspect-Based Sentiment Analysis for Polarity Estimation of Customer Reviews on Twitter”, Computers, Materials and Continua, 2021, doi: 10.32604/cmc.2021.014226.
[7]N. Ayub, M. Talib, R. Hanif, and M.K. Awais, “Aspect Extraction Approach for Sentiment Analysis Using Key- words”, Computers, Materials and Continua, vol. 74, pp. 6879-6892, 2023, doi:10.32604/cmc.2023.034214.
[8]P. Mishra and S.K. Panda, “Dependency structure-based rules using root node technique for explicit aspect extraction from online reviews”, IEEE Access, 2023, pp. 30217-30229, doi:10.1109/ACCESS.2023.3287830.
[9]G. Hinton and T.J. Sejnowski, “Unsupervised learning: foundations of neural computation”, MIT press, 1999, doi:10.7551/mitpress/7011.001.0001.
[10]S. Moghaddam and M. Ester, “Interdependent lda model for learning latent aspects and their ratings from online product reviews”, Proceedings of the 19th ACM international conference on Information and knowledge management, 2010, pp. 665-674, doi:10.1145/2009916.2010006.
[11]S. Shariaty and S. Moghaddam, “Fine-grained opinion mining using conditional random fields”, IEEE 11th International Conference on Data Mining Workshops, vol. 10, pp. 270-277, 2011, doi:10.1109/ICDMW.2011.85.
[12]V.S. Anoop and S. Asharaf, “Aspect-oriented sentiment analysis: a topic modeling-powered approach”, Journal of Intelligent Systems, vol. 29, pp. 1166-1178, 2018, doi:10.1515/jisys-2018-0299.
[13]B. Ozyurt and M.A. Akcayol, “A new topic modeling based approach for aspect extraction in aspect based sentiment analysis: SS-LDA”, Expert Systems with Applications, vol. 168, pp. 1114-1231, 2021, doi: 10.1016/j.eswa.2020.114231.
[14]T. Heinrich and F. Marchi, “Teamufpr at absapt 2022: Aspect extraction with CRF and BERT”, Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2022), 2022.
[15]S. Dargan, M. Kumar, M.R. Ayyagari, and G. Kumar, “A survey of deep learning and its applications: a new paradigm to machine learning”, Archives of Computational Methods in Engineering, vol 27, pp. 1071-1092, 2020.
[16]I.H. Sarker, “Deep learning: A comprehensive overview of techniques, taxonomy, applications, and research directions”, SN Computer Science, vol. 6, pp. 1-20, 2021, doi: 10.1007/s42979-021-00815-1.
[17]S. Hammi, S. M. Hammami, and L. H. Belguith, “Deep Learning Models for Aspect-Based Sentiment Analysis Task: A Survey Paper”, International Conference on Intelligent Systems and Pattern Recognition, Cham: Springer Nature Switzerland, 2023, pp. 169-183, doi: 10.1109/MLISE54096.2021.00056.
[18]S. Ruder, P. Ghaffari, and J.G. Breslin, “Insight-1 at SemEval-2016 Task 5: Deep learning for multilingual aspect- based sentiment analysis”, arXiv preprint arXiv:1609.02748, 2016, doi: 10.18653/v1/S16-1053.
[19]G. Zheng, J. Wang, L. Yu, and X. Zhang, “A hybrid approach for aspect sentiment triplet extraction via reinforcement learning and adversarial training”, Expert Systems with Applications, vol. 184, pp. 115-546, 2023, doi: 10.1145/3614008.3614054.
[20]R. He, W.S. Lee, H. Neg, and D. Dahlmeier, “An interactive multi-task learning network for end-to-end aspect-based sentiment analysis”, arXiv preprint arXiv:1906.06906, 2019, doi: 10.18653/v1/P19-1048.
[21]S. Chen, Y. Wang, J. Liu, and Y. Wang, “Bidirectional machine reading comprehension for aspect sentiment triplet extraction”, Proceedings of The AAAI Conference On Artificial Intelligence, vol. 35, pp. 12666-12674, 2021, doi: 10.48550/arXiv.2103.07665.
[22]K. Sharbatian and M.H. Moattar, “Deep aspect extraction and classification for opinion mining in e-commerce applications using convolutional neural network feature extraction followed by long short term memory attention model”, Applied AI Letters, vol. 4, pp-86-93, 2023, doi: 10.1002/ail2.86.
[23]N. Liu and B. Shen, “Aspect term extraction via information-augmented neural network”, Complex and Intelligent Systems, vol. 9, pp.537-563, 2023, doi:10.1007/s40747-022-00818-2.
[24]S. Hammi, S.M. Hammami, and L.H. Belguith, “FreMPhone: A French Mobile Phone Corpus for Aspect-Based Sentiment Analysis”, International Conference on Computational Collective Intelligence, Cham: Springer Nature Switzerland, 2023, pp. 237-249.
[25]S. Poria, E. Cambria, and A. Gelbukh, “Aspect extraction for opinion mining with a deep convolutional neural network”, Knowledge-Based Systems, vol. 108, pp. 42-49, 2016, doi: 10.1016/j.knosys.2016.06.009.
[26]A. Laddha and A. Mukherjee, “Aspect Specific Opinion Expression Extraction using Attention based LSTM-CRF Network”, International Conference on Computational Linguistics and Intelligent Text Processing, vol. 20, pp. 442- 454, 2019, doi: 10.48550/arXiv.1902.02709.
[27]G. Ansari, C. Saxena, T. Ahmad, and M.N. Doja, “Aspect term extraction using graph-based semi-supervised learning”. Procedia Computer Science, vol. 167, pp. 2080-2090, 2020, doi: 10.1016/j.procs.2020.03.249.
[28]B. Ozyurt and M.A. Akcayol, “A new topic modeling based approach for aspect extraction in aspect based sentiment analysis: SS-LDA”, Expert Systems with Applications, vol. 168, pp. 114-231, 2021, doi: 10.1016/j.eswa.2020.114231.
[29]P. Ray and A. Chakrabarti, “A mixed approach of deep learning method and rule-based method to improve aspect level sentiment analysis”, Applied Computing and Informatic, vol.18, pp.163-178, 2022, doi: 10.1016/j.aci.2019.02.002.
[30]S. Hammi, S.M. Hammami, and L.H. Belguith, “An improved hybrid method for sentiment analysis”, International conference on innovations in intelligent systems and applications (INISTA), IEEE, pp. 1-6. 2022, doi: 10.1109/IN- ISTA55318.2022.9894143.
[31]Y. Zhao, X. Mao, Z. Liu, and Y. Li, “Aspect sentiment classification with both word-level and aspect-level attention networks”, IEEE Access, vol. 7, pp. 61832-61841, 2019, doi: 10.24963/ijcai.2018/617.
[32]L. Yao, C. Mao, R. Yan, Y. Li, and J. Huang, “Incorporating local dependency model into topic model for aspect term extraction in sentiment analysis”, Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 10-20, 2019, doi: 10.1016/j.ins.2018.04.079.
[33]R. Agrawal and R. Srikant, “Fast algorithms for mining association rules”, Proc. 20th int. conf. very large data bases, VLDB, vol. 1215, pp. 478-499, 1994.
[34]S. Hammi, S.M. Hammami, and L.H. Belguith, “Advancing aspect-based sentiment analysis with a novel architecture combining deep learning models CNN and bi-RNN with the machine learning model SVM”, Social Network Analysis and Mining, Springer, 2022, pp. 97-117, doi: 10.1007/s13278-023-01126-4.
[35]N. Kooli and E. Pigneul, “Analyse de sentiments à base d’aspects par combinaison de réseaux profonds : application à des avis en Français”, Conférence sur le Traitement Automatique des Langues Naturelles (TALN), 2018.
[36]B. Kane, A. Jrad, A. Essebbar, O. Guinaudeau, V. Chiesa, I. Quénel et al., “CNN-LSTM-CRF for Aspect-Based Sentiment Analysis: A Joint Method Applied to French Reviews”, Proceedings of the 14th International Conference on Advanced Applied Computing (ICAART), vol. 1, pp. 498-505, 2021.